Similar Items: Disentangled representations in speech processing applications
- A digital filter bank cochlear model for speech pre-processing
- Unsupervised feature learning for speech using correspondence and Siamese networks
- Multilingual acoustic word embeddings for zero-resource languages
- Adaptive estimation of speech parameters
- Sustained learning for a speech recognition system
- Automatic syllabification of untranscribed speech
Author: Kamper, Herman
- Spoken language modeling with discrete units
- Direct and indirect multimodal few-shot learning of speech and images
- Multilingual acoustic word embeddings for zero-resource languages
- Semi-supervised machine learning for livestock threat classification using gps data
- Visually grounded speech models for low-resource languages and cognitive modelling
- Learning to speak and hear through multi-agent communication over a continuous acoustic channel